© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8771
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    tatus
    -0.07
    tsky
    -0.07
    𬯎
    -0.07
    extrême
    -0.06
    deprecated
    -0.06
     depth
    -0.06
    켑
    -0.06
     generado
    -0.06
    쉥
    -0.06
    党的建设
    -0.06
    POSITIVE LOGITS
     משמעותי
    0.07
    室
    0.07
    Amt
    0.07
    してくれる
    0.07
    两三
    0.07
    _dx
    0.07
    及
    0.07
    ('-
    0.06
    男方
    0.06
     treatments
    0.06
    Activations Density 0.001%

    No Known Activations