INDEX

Explanations

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.tie

-0.28

ancell

-0.25

 Corpus

-0.25

wc

-0.25

xAA

-0.24

xCF

-0.24

otics

-0.24

ABCDE

-0.24

tai

-0.24

 matter

-0.24

POSITIVE LOGITS

æĩ¦

0.29

 deduct

0.28

streams

0.26

 stream

0.26

stream

0.26

ç¡®ç«ĭ

0.26

ream

0.25

éĢ¶

0.25

caster

0.25

rik

0.25

Activations Density 0.002%

the

No Comments

No Known Activations