INDEX

Explanations

start of articles/snippets

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tement

-0.29

 háº£i

-0.25

ADIO

-0.25

ibox

-0.25

,[],

-0.25

å°¼æĸ¯

-0.25

uco

-0.25

è°İè¨Ģ

-0.25

éĢ±

-0.25

åħ¶ä¸Ńä¹ĭä¸Ģ

-0.24

POSITIVE LOGITS

plers

0.27

thesize

0.27

KeyType

0.27

swe

0.26

acular

0.26

åµ´

0.26

ï¿½t

0.26

ipple

0.25

å¯Ĩ

0.24

 uncert

0.24

Activations Density 0.004%

start of articles/snippets

No Comments

No Known Activations