INDEX

Explanations

competence

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

(indent

-0.27

Indented

-0.25

WHO

-0.25

edException

-0.25

Ist

-0.24

ITS

-0.24

uD

-0.24

 infring

-0.24

uu

-0.24

infer

-0.24

POSITIVE LOGITS

reich

0.26

argas

0.26

ormal

0.25

 critics

0.25

erness

0.24

erty

0.24

ough

0.24

åıĪæĺ¯

0.24

ä¾¿æĺ¯

0.24

Ð½Ð¾Ð»Ð¾Ð³

0.24

Activations Density 0.001%

competence

No Comments

No Known Activations