INDEX

Explanations

web text 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

(mt

-0.27

å¿«è®¯

-0.27

 stead

-0.26

éĹªçĶµ

-0.26

quat

-0.25

ozo

-0.25

 Rough

-0.25

OID

-0.24

éªł

-0.24

cial

-0.24

POSITIVE LOGITS

åħ³

0.28

æ²»

0.26

Zwe

0.25

pute

0.25

æĺ¯ä¸ª

0.25

å¢ŀéĩı

0.25

ÐĹÐ°

0.25

bers

0.24

éĽ¶éĥ¨ä»¶

0.24

bek

0.24

Activations Density 0.002%

web text snippets

No Comments

No Known Activations