INDEX

Explanations

journalism and commentary

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ussion

-0.28

slope

-0.27

_guide

-0.26

éĶ¦æłĩ

-0.26

-guide

-0.25

SWG

-0.24

 willen

-0.24

 nonatomic

-0.24

fetch

-0.24

 FETCH

-0.24

POSITIVE LOGITS

Int

0.29

ew

0.29

int

0.27

int

0.27

em

0.26

Int

0.26

å¹´åºķ

0.26

ç«Ļ

0.26

_int

0.25

æĢ»éĥ¨

0.25

Activations Density 0.789%

journalism and commentary

No Comments

No Known Activations