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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 25955
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tells
    -0.08
     Qual
    -0.07
     �
    -0.07
    .isUser
    -0.07
     informs
    -0.07
     �
    -0.07
    hits
    -0.07
    Sing
    -0.07
    Overrides
    -0.07
     Holl
    -0.06
    POSITIVE LOGITS
     سنة
    0.08
    起来
    0.08
     przed
    0.07
    .base
    0.07
    paces
    0.07
    一起
    0.07
    (results
    0.07
    박
    0.07
    iddleware
    0.07
    ilage
    0.07
    Activations Density 0.006%

    No Known Activations