INDEX

Explanations

activist

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

.codec

-0.27

æĺ¥æĻļ

-0.27

WithPath

-0.26

ä¸ĭåįĬ

-0.26

eka

-0.26

ä¹³

-0.25

Lak

-0.24

 sorte

-0.24

å¸Ĥéķ¿

-0.24

çŁ¢

-0.24

POSITIVE LOGITS

bers

0.30

 inconsistency

0.28

quare

0.28

ber

0.28

 butter

0.27

BER

0.27

ä¸Ģèĩ´æĢ§

0.27

virt

0.27

roy

0.26

 consistency

0.26

Activations Density 0.334%

activist

No Comments

No Known Activations