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

    Neuronpedia

    APICircuit 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. 72492
    Prev
    Next
    INDEX
    Explanations

    free markets

    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
    	Check
    -0.07
    Voice
    -0.07
    Burn
    -0.07
    _packet
    -0.07
    _move
    -0.07
    Recv
    -0.07
    沉浸
    -0.06
    .Areas
    -0.06
    _dataset
    -0.06
    _peak
    -0.06
    POSITIVE LOGITS
    揉
    0.08
     Samurai
    0.07
    .random
    0.07
     rej
    0.07
     sodium
    0.07
    媱
    0.07
     humorous
    0.06
     ruthless
    0.06
    家长们
    0.06
     aerospace
    0.06
    Activations Density 0.002%

    No Known Activations