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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 59482
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ╊
    -0.08
    🚌
    -0.07
    厥
    -0.07
    ollah
    -0.07
    _permission
    -0.07
    迷失传奇
    -0.07
    铙
    -0.07
    ⊔
    -0.07
    觟
    -0.07
    ☧
    -0.07
    POSITIVE LOGITS
     Rates
    0.08
    成為
    0.08
     label
    0.07
     exercised
    0.07
    Wi
    0.07
     stainless
    0.07
    -metal
    0.06
    MessageBox
    0.06
    Intensity
    0.06
     finished
    0.06
    Activations Density 0.007%

    No Known Activations