INDEX

Explanations

varied, long-form text

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

 binnen

-0.26

Ta

-0.26

å®ĿçŁ³

-0.25

 Whitney

-0.25

.Tasks

-0.24

 Autom

-0.24

GX

-0.24

ta

-0.24

ountain

-0.24

è·¸

-0.23

POSITIVE LOGITS

(-(

0.26

ç½ĳè®¯

0.26

Ļ¨

0.25

éĺħè¯»åħ¨æĸĩ

0.25

 scale

0.25

 ë°°

0.24

ogie

0.24

thers

0.24

 tact

0.23

 tort

0.23

Activations Density 0.229%

varied, long-form text

No Comments

No Known Activations