INDEX

Explanations

negative consequences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

consult

-0.28

bill

-0.26

orna

-0.25

UCH

-0.24

<boost

-0.24

acakt

-0.24

.layer

-0.23

Layer

-0.23

Leaks

-0.23

 freder

-0.23

POSITIVE LOGITS

æĹħéĢĶ

0.29

erate

0.26

opsis

0.25

eated

0.25

cles

0.24

_tokenize

0.24

ifo

0.24

cor

0.23

 absor

0.23

 viol

0.23

Activations Density 5.083%

negative consequences

No Comments

No Known Activations