INDEX

Explanations

5

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

losure

-0.28

aty

-0.28

quet

-0.28

/MIT

-0.27

å·¥ç¨ĭé¡¹çĽ®

-0.26

åģļä¸įåĪ°

-0.25

 regression

-0.25

round

-0.25

osit

-0.24

åĺĽ

-0.24

POSITIVE LOGITS

aldi

0.27

occ

0.26

 Äĳua

0.26

 wrap

0.25

è¯°

0.25

alli

0.24

 Philipp

0.24

Occ

0.24

 spice

0.24

é¸¬

0.24

Activations Density 0.001%

5

No Comments

No Known Activations