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. 88480
    Prev
    Next
    INDEX
    Explanations

    Windows

    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
    /graphql
    -0.07
    @JsonProperty
    -0.07
    $smarty
    -0.07
     אישית
    -0.07
     csvfile
    -0.07
     paperwork
    -0.07
    (HttpContext
    -0.07
     fd
    -0.07
     commenced
    -0.07
     accordance
    -0.06
    POSITIVE LOGITS
    친
    0.07
     Supporters
    0.07
    避
    0.07
     가치
    0.07
    ????
    0.06
    ierten
    0.06
    ocation
    0.06
    -shop
    0.06
    Additional
    0.06
     Background
    0.06
    Activations Density 0.039%

    No Known Activations