INDEX

Explanations

immunology and medical research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĿ¡

-0.35

illon

-0.27

CEE

-0.26

thesis

-0.26

ç®Ń

-0.25

åĨ¬

-0.25

ä¸Ĭä¸ĭ

-0.24

Cour

-0.24

 Carlo

-0.24

 Patri

-0.24

POSITIVE LOGITS

çĽ¸åħ³æĶ¿çŃĸ

0.26

å¦Ĥæľīä¾µæĿĥ

0.26

 ImmutableList

0.26

 online

0.26

 crossed

0.25

 pred

0.25

pred

0.24

Pred

0.24

 exem

0.24

cker

0.24

Activations Density 0.013%

immunology and medical research

No Comments

No Known Activations