INDEX

Explanations

Moore

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

uit

-0.28

 Exclude

-0.25

-rays

-0.25

 stir

-0.25

overwrite

-0.24

riv

-0.24

rays

-0.24

 steadily

-0.24

warf

-0.23

ä¸įåľ¨ä¹İ

-0.23

POSITIVE LOGITS

åłµ

0.27

 Barr

0.26

æĭ¦

0.25

.KeyCode

0.25

ÑĢÐ¾ÑģÑģ

0.24

é«ĺå³°

0.24

ARR

0.24

Arr

0.24

Leod

0.24

 burden

0.24

Activations Density 0.004%

Moore

No Comments

No Known Activations