INDEX

Explanations

often

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

 breath

-0.27

éĩį

-0.25

ighbor

-0.25

lÃ¢

-0.25

 Facing

-0.25

,cv

-0.25

 Ð½Ð°Ð¿ÑĢÐ°Ð²

-0.24

exual

-0.24

Hod

-0.23

éĩĮç¨ĭ

-0.23

POSITIVE LOGITS

out

0.26

 Matches

0.26

ÑĮÑĤÐµ

0.26

 infl

0.25

 retrieves

0.25

SQ

0.25

 accuses

0.24

 Atlanta

0.24

funcs

0.24

SQ

0.23

Activations Density 0.002%

often

No Comments

No Known Activations