INDEX

Explanations

Voice-related technologies/acting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

azio

-0.27

teness

-0.26

ç»ĨåĪĨ

-0.25

åŀĽ

-0.24

çº¶

-0.24

genden

-0.24

minate

-0.23

andez

-0.23

oma

-0.23

lagen

-0.23

POSITIVE LOGITS

dot

0.31

dot

0.30

atable

0.30

(dot

0.27

éĵ±

0.26

åĭĥ

0.26

è¾Ĳ

0.26

DOT

0.24

acky

0.24

ible

0.24

Activations Density 0.002%

Voice-related technologies/acting

No Comments

No Known Activations