INDEX

Explanations

Code and technical text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å±ħ

-0.27

 rebound

-0.27

ELY

-0.26

ayed

-0.26

elia

-0.25

 participation

-0.24

elli

-0.24

Responder

-0.24

 increased

-0.24

ä¸įå½ĵ

-0.23

POSITIVE LOGITS

 newText

0.28

æĤ¼

0.28

nj

0.28

nov

0.27

neg

0.27

æ´Ĺ

0.27

new

0.26

.neg

0.26

dj

0.25

 newest

0.25

Activations Density 0.005%

Code and technical text

No Comments

No Known Activations