Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 43830
    Prev
    Next
    INDEX
    Explanations

    so

    np_max-act-logits · gemini-2.0-flash

    low-quality, spam, or adult content in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @xiaoqingsun004
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.08
     benefici
    -0.07
     dew
    -0.07
    idUser
    -0.07
     podrá
    -0.07
     Older
    -0.07
     достаточно
    -0.07
    𝑼
    -0.06
    _invoice
    -0.06
     USER
    -0.06
    POSITIVE LOGITS
    Two
    0.07
    iddleware
    0.07
     rue
    0.07
    (CL
    0.06
    (varargin
    0.06
    igrams
    0.06
    鬧
    0.06
     $\
    0.06
    Place
    0.06
    有机结合
    0.06
    Activations Density 0.107%

    No Known Activations