INDEX

Explanations

neighbor

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sky

-0.30

DER

-0.27

DER

-0.24

glas

-0.24

æĶ¿åħļ

-0.24

stick

-0.24

rtc

-0.24

Bro

-0.24

ffb

-0.24

çİ©æ³ķ

-0.23

POSITIVE LOGITS

hood

0.29

oot

0.28

maid

0.27

ä»¬

0.27

neath

0.27

ä¹ĭä½ľ

0.26

_cf

0.26

hips

0.24

ole

0.24

ARGS

0.24

Activations Density 0.303%

neighbor

No Comments

No Known Activations