INDEX

Explanations

want

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

éĻ°

-0.30

reau

-0.30

<Tag

-0.27

ä¸ĢåĽŀäºĭ

-0.27

eos

-0.26

è¿ĺæĥ³

-0.26

æĪĳä»¬è®¤ä¸º

-0.25

åĽŀäºĭ

-0.25

_filled

-0.24

undle

-0.24

POSITIVE LOGITS

 period

0.30

ä¸ºæľŁ

0.29

amed

0.29

Period

0.27

apters

0.27

 Period

0.27

period

0.26

cestor

0.26

æľŁéĻĲ

0.26

Activations Density 0.076%

want

No Comments

No Known Activations