INDEX

Explanations

#

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

å±ĭ

-0.33

plots

-0.28

 Plumbing

-0.28

 roof

-0.26

roof

-0.26

 means

-0.25

 exits

-0.25

numeric

-0.24

åŁºæľ¬æĥħåĨµ

-0.24

 visual

-0.24

POSITIVE LOGITS

spiel

0.29

ç¨½

0.28

urance

0.28

çī¹åĪ«å£°æĺİ

0.27

anken

0.27

å¡¾

0.27

 Scient

0.24

LOUD

0.24

;]/

0.24

 STILL

0.24

Activations Density 0.017%

#

No Comments

No Known Activations

#

No Comments

No Known Activations