INDEX

Explanations

Technical documentation/code snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

Equ

-0.27

 picks

-0.27

Equ

-0.24

ivel

-0.24

Ð¾ÑĢÐ¼

-0.24

 pick

-0.24

 throws

-0.24

irma

-0.24

oken

-0.24

Pick

-0.24

POSITIVE LOGITS

 reusable

0.30

reuse

0.30

 mixins

0.29

mts

0.28

 versatility

0.28

 customizable

0.28

åĪĨç¦»

0.27

sein

0.27

 separation

0.27

å®ļåĪ¶

0.27

Activations Density 0.003%

Technical documentation/code snippets

No Comments

No Known Activations