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. 48314
    Prev
    Next
    INDEX
    Explanations

    Relationships between items

    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
    -java
    -0.07
    fm
    -0.06
     להבין
    -0.06
    $c
    -0.06
     inlet
    -0.06
    ↵	
    ↵
    -0.06
     cloves
    -0.06
    cers
    -0.06
    漳州
    -0.06
    _ENGINE
    -0.06
    POSITIVE LOGITS
     strftime
    0.07
    izophren
    0.07
    .FromResult
    0.07
     Chunk
    0.07
    identifier
    0.07
    müş
    0.07
    ->{_
    0.06
    嗦
    0.06
    立志
    0.06
    隶属于
    0.06
    Activations Density 0.183%

    No Known Activations