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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109832
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act-logits · gemini-2.0-flash
    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
    <context
    -0.07
     врач
    -0.07
    醫生
    -0.07
    ผลงาน
    -0.06
    终于
    -0.06
     ambulance
    -0.06
    投保
    -0.06
    Combo
    -0.06
    .once
    -0.06
    @store
    -0.06
    POSITIVE LOGITS
     lab
    0.08
    连载
    0.07
     Dissertation
    0.07
    得不到
    0.07
     stripslashes
    0.07
     paperback
    0.07
     Anc
    0.07
     definition
    0.07
     standards
    0.07
    前述
    0.06
    Activations Density 0.198%

    No Known Activations