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. 71692
    Prev
    Next
    INDEX
    Explanations

    Legal cases and states

    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
     Toast
    -0.08
    -xl
    -0.07
    .com
    -0.07
    _DATABASE
    -0.07
    一站式
    -0.07
    _original
    -0.07
    胡萝卜
    -0.07
    /json
    -0.07
    炒
    -0.06
    .figure
    -0.06
    POSITIVE LOGITS
     bölges
    0.07
     Finals
    0.07
    ():↵
    0.07
    Industry
    0.07
    ]));
    ↵
    0.07
     Gäste
    0.07
    מלך
    0.07
     interle
    0.07
    _properties
    0.07
     pilots
    0.07
    Activations Density 0.010%

    No Known Activations