INDEX

Explanations

Biology and medicine texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

Fa

-0.28

è¿¹

-0.28

è¾¹

-0.27

æľ½

-0.26

 inputs

-0.26

cro

-0.26

Cro

-0.25

SON

-0.25

Cro

-0.24

ixed

-0.24

POSITIVE LOGITS

distance

0.25

 remot

0.25

 distance

0.25

åĨįæĿ¥

0.25

ctors

0.24

éĥ½èĥ½å¤Ł

0.24

translator

0.24

Remote

0.24

ä¼ģä¸ļåıĳå±ķ

0.24

éĢļçķħ

0.23

Activations Density 0.000%

Biology and medicine texts

No Comments

No Known Activations